论文标题
Decanus到Legatus：2d-3d人姿势提升的合成训练
Decanus to Legatus: Synthetic training for 2D-3D human pose lifting
论文作者
论文摘要
3D人姿势估计是一项具有挑战性的任务，因为很难在受控环境之外获取地面真相数据。 A number of further issues have been hindering progress in building a universal and robust model for this task, including domain gaps between different datasets, unseen actions between train and test datasets, various hardware settings and high cost of annotation, etc. In this paper, we propose an algorithm to generate infinite 3D synthetic human poses (Legatus) from a 3D pose distribution based on 10 initial handcrafted 3D poses (Decanus) during the training 2至3D人类姿势举重神经网络我们的结果表明，我们可以使用专用数据集中的实际数据实现3D姿势估计性能，但可以在零弹射设置中实现方法，显示了我们框架的概括潜力。
3D human pose estimation is a challenging task because of the difficulty to acquire ground-truth data outside of controlled environments. A number of further issues have been hindering progress in building a universal and robust model for this task, including domain gaps between different datasets, unseen actions between train and test datasets, various hardware settings and high cost of annotation, etc. In this paper, we propose an algorithm to generate infinite 3D synthetic human poses (Legatus) from a 3D pose distribution based on 10 initial handcrafted 3D poses (Decanus) during the training of a 2D to 3D human pose lifter neural network. Our results show that we can achieve 3D pose estimation performance comparable to methods using real data from specialized datasets but in a zero-shot setup, showing the generalization potential of our framework.
